Discussion among Different Methods of Updating Model Filter in Object Tracking
This work provides a systematic comparison of filter update techniques for researchers in visual object tracking, but it is incremental as it synthesizes existing methods rather than introducing new ones.
The paper analyzes different methods for updating model filters in discriminative correlation filter (DCF)-based object tracking algorithms, deducing relationships between kernel trick, frequency domain, and spatial domain approaches, and validating these through comparative experiments and filter visualizations.
Discriminative correlation filters (DCF) have recently shown excellent performance in visual object tracking area. In this paper, we summarize the methods of updating model filter from discriminative correlation filter (DCF) based tracking algorithms and analyzes similarities and differences among these methods. We deduce the relationship between updating coefficient in high dimension (kernel trick), updating filter in frequency domain and updating filter in spatial domain, and analyze the difference among these different ways. We also analyze the difference between the updating filter directly and updating filter's numerator (object response power) with updating filter's denominator (filter's power). The experiments about comparing different updating methods and visualizing the template filters are used to prove our derivation.